swarm-planner
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are focused on legitimate implementation planning and architectural research. No malicious code or suspicious behaviors were detected.
- [PROMPT_INJECTION]: The skill uses instructional keywords like 'IMPORTANT' and 'CRITICAL' for flow control and task prioritization. These do not attempt to bypass safety filters or override core agent constraints.
- [DATA_EXFILTRATION]: No patterns indicating the access of sensitive files (e.g., SSH keys, environment variables) or the unauthorized transmission of data to external servers were identified.
- [REMOTE_CODE_EXECUTION]: The skill does not contain instructions to download or execute remote scripts. References to package installation in the templates are for illustrative planning purposes and not for execution by the agent.
Audit Metadata